Protection of neural networks by obfuscation of activation functions
US12099622B2 · kind B2 · utility
0Cited by
10References
20Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Dec 16, 2021 |
| Grant date | Sep 24, 2024 |
| Priority date | — |
| Expiry date | Mar 31, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V10/82
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Aspects of the present disclosure involve implementations that may be used to protect neural network models against adversarial attacks by obfuscating neural network operations and architecture. Obfuscation techniques include obfuscating weights and biases of neural network nodes, obfuscating activation functions used by neural networks, as well as obfuscating neural network architecture by introducing dummy operations, dummy nodes, and dummy layers into the neural networks.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.